AI keyword suggestions

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false and openWorldHint=true, so the agent knows this is a non-read, model-driven operation. The description adds real value beyond that by disclosing the side effect — results are written into the 'idea' section rather than returned inline or added as live keywords — which is the single most important behavioral fact here. It stops short of stating cost, rate limits, or AI-provider preconditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the action and ends with the consequential outcome (where the results land). Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly tells the agent where results end up, which is the key return-value fact. Given openWorldHint and the presence of AI-status siblings, it would be more complete if it mentioned the AI provider requirement or the non-deterministic/costly nature of generation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so hint, count and projectId are already fully documented in the schema. The description adds no further meaning about how hint steers output or how it interacts with the existing board, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and outcome: ask the AI to generate new keyword ideas for a project, sourced from its listing, brief and current board. That is more concrete than the title alone, though it does not distinguish itself from the similarly-named sibling brainstorm_project, which an agent could easily confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'new keyword ideas' and the result landing in the idea section, so an agent can infer this is a discovery step rather than a commit step. But there is no explicit when-to-use, no exclusion such as preferring brainstorm_project for freeform ideation, and no prerequisite noted (e.g. an AI provider must be configured, per the existence of get_ai_status/set_ai_provider siblings).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.